Changes for new thinking format and URL format

[pamelafox]

Purpose

This pull request includes updates to the Azure infrastructure configuration, refactors the OpenAI client integration in the Quart app, and simplifies the chat response streaming logic. Additionally, it includes a minor fix in the front-end template for handling response content.

Infrastructure Updates:

• Updated aiServicesEndpoint in infra/main.bicep to remove the /models suffix in both the module definition and the output AZURE_INFERENCE_ENDPOINT. This ensures consistency with the new endpoint format. [1] [2]

OpenAI Client Refactoring:

• Replaced the AsyncOpenAI client with AsyncAzureOpenAI in src/quartapp/chat.py. This change removes the custom TokenBasedAuth class and simplifies authentication by directly using the Azure AD token provider. The API version was also updated to 2025-04-01-preview. [1] [2]

Chat Response Streaming Simplification:

• Simplified the logic in async def response_stream() by removing handling for <think> tags and directly yielding the JSON representation of the model's response updates.

Front-End Template Fix:

• Adjusted the condition in src/quartapp/templates/index.html to ensure the loading bar is hidden only when event.delta.content is present.

Does this introduce a breaking change?

[ ] Yes
[ ] No

Pull Request Type

What kind of change does this Pull Request introduce?

[ ] Bugfix
[ ] Feature
[ ] Code style update (formatting, local variables)
[ ] Refactoring (no functional changes, no api changes)
[ ] Documentation content changes
[ ] Other... Please describe:

How to Test

• Get the code

git clone [repo-address]
cd [repo-name]
git checkout [branch-name]
npm install

• Test the code

What to Check

Verify that the following are valid

• ...

Other Information